sensors
Article
Design of a New Method for Detection of Occupancy
in the Smart Home Using an FBG Sensor
Jan Vanus1,* , Jan Nedoma2 , Marcel Fajkus2 and Radek Martinek1
1 Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB–Technical University of Ostrava, 708 33 Ostrava, Czech Republic; [email protected] 2 Department of Telecommunications, Faculty of Electrical Engineering and Computer Science, VSB–Technical
University of Ostrava, 708 33 Ostrava, Czech Republic; [email protected] (J.N.); [email protected] (M.F.)
* Correspondence: [email protected]
Received: 29 November 2019; Accepted: 6 January 2020; Published: 10 January 2020
Abstract:This article introduces a new way of using a fibre Bragg grating (FBG) sensor for detecting the presence and number of occupants in the monitored space in a smart home (SH). CO2sensors are used to determine the CO2concentration of the monitored rooms in an SH. CO2sensors can also be used for occupancy recognition of the monitored spaces in SH. To determine the presence of occupants in the monitored rooms of the SH, the newly devised method of CO2prediction, by means of an artificial neural network (ANN) with a scaled conjugate gradient (SCG) algorithm using measurements of typical operational technical quantities (indoor temperature, relative humidity indoor and CO2 concentration in the SH) is used. The goal of the experiments is to verify the possibility of using the FBG sensor in order to unambiguously detect the number of occupants in the selected room (R104) and, at the same time, to harness the newly proposed method of CO2prediction with ANN SCG for recognition of the SH occupancy status and the SH spatial location (rooms R104, R203, and R204) of an occupant. The designed experiments will verify the possibility of using a minimum number of sensors for measuring the non-electric quantities of indoor temperature and indoor relative humidity and the possibility of monitoring the presence of occupants in the SH using CO2prediction by means of the ANN SCG method with ANN learning for the data obtained from only one room (R203). The prediction accuracy exceeded 90% in certain experiments. The uniqueness and innovativeness of the described solution lie in the integrated multidisciplinary application of technological procedures (the BACnet technology control SH, FBG sensors) and mathematical methods (ANN prediction with SCG algorithm, the adaptive filtration with an LMS algorithm) employed for the recognition of number persons and occupancy recognition of selected monitored rooms of SH.
Keywords: smart home (SH); prediction; artificial neural network (ANN); fiber bragg grating (FBG); occupancy; number of person recognition; scaled conjugate gradient (SCG)
1. Introduction
Recognizing the occupancy, number of individuals, location-and-movement recognition and activity recognition of an individual in an indoor space is one the key functionalities of a smart home (SH), as a prerequisite to providing services to support independent living of elderly SH occupants and has a great influence on internal loads and HVAC (heating, ventilation and air conditioning) requirement, thus increasing the energy consumption optimization. Azghandi et al. focused on the particular case of an SH with multiple occupants, they developed a location-and-movement recognition method using many inexpensive passive infrared (PIR) motion sensors and a small number of more
Sensors2020,20, 398 2 of 31
costly radio frequency identification (RFID) readers [1]. Benmansour et al. provided an overview of existing approaches and current practices for activity recognition in multi-occupant SHs [2]. Braun et al. reported the investigation of two categories of occupancy sensors with the requirements of supporting wireless communication and a focus on the low cost of the systems (capacitive proximity sensors and accelerometers that are placed below the furniture) with a classification accuracy between 79% and 96% [3]. Chan et al. proposed the methodology and design of a voice-controlled environment, with an emphasis on speech recognition and voice control, based on Amazon Alexa and Raspberry Pi in an SH [4]. Chen et al. proposed an activity recognition system guided by an unobtrusive sensor (ARGUS) with a facing direction detection accuracy, resulting from manually defined features, that reached 85.3%, 90.6%, and 85.2% [5]. Khan et al. developed a low-cost heterogeneous radar-based activity monitoring (RAM) system for recognizing fine-grained activities in an SH with detecting accuracy of 92.84% [6]. Lee et al. investigated the use of cameras and a distributed processing method for the automated control of lights in an SH, which provided occupancy reasoning and human activity analysis [7]. Mokhtari et al. proposed a new human identification sensor, which can efficiently differentiate multiple residents in a home environment to detect their height as a unique bio-feature with three sensing/communication modules: pyroelectric infrared (PIR) occupancy, ultrasound array, and Bluetooth low-energy (BLE) communication modules [8]. A new recognition algorithm for household appliances, based on a Bayes classification model, is presented by Yan et al., in which sequential appliance power consumption data from intelligent power sockets is used and for the generalization and extraction of the characteristics of occupant behavior and power consumption of typical household appliances [9]. Yang et al. proposed a novel indoor tracking technique for SHs with multiple residents by relying only on non-wearable, environmentally deployed sensors such as passive infrared motion sensors [10]. Feng et al. presented a novel real-time, device-free, and privacy-preserving WiFi-enabled Internet of Things (IoT) platform for SH-occupancy sensing, which can promote a myriad of emerging applications with an accuracy of 96.8% and 90.6% in terms of occupancy detection and recognition, respectively [11]. Traditionally, in building energy modeling (BEM) programs, occupant behavior (OB) inputs are deterministic and less indicative of real-world scenarios, contributing to discrepancies between simulated and actual energy use in buildings. Yin et al. (2016) presented a new OB modeling tool, with an occupant behavior functional mock-up unit (obFMU) that enables co-simulation with BEM programs implementing a functional mock-up interface (FMI) [12]. Occupants are involved in a variety of activities in buildings, which drive them to move among rooms, enter or leave a building. Hong et al. (2016) defined SH occupancy using four parameters and showed how they varied with time. The four occupancy parameters were as follows: (1) the number of occupants in a building, (2) occupancy status of space, (3) the number of occupants in a space, and (4) the location of an occupant [13].
In order to detect the occupancy of the SH by indirect methods (without using cameras), common operational and technical sensors are used in this article to measure the indoor temperature, the indoor relative humidity and the CO2indoor concentration within the BACnet technology for HVAC control. A fibre Bragg grating (FBG) sensor will be used to detect the number of occupants in the monitored space of room R104 (ground floor). The method devised for the prediction of the CO2waveform using artificial neural network (ANN) scaled conjugate gradient (SCG) will be verified during the experiments conducted to detect the occupancy of rooms R104, R203 and R204. The input quantities measured to ANN SCG were obtained from the indoor temperature and relative indoor humidity sensors. One of the objectives of the article is to verify the possibility of minimizing investment costs by using cheaper temperature and relative humidity sensors instead of a more expensive CO2sensor to detect the occupancy of monitored SH spaces. The other objectives of this article are the following: 1. Experimental verification of FBG sensor use for the recognition of the number occupants in SH
room R104.
2. Experimental verification of the CO2concentration measurement in an SH by means of common operational sensors for the occupancy status of the SH space.
Sensors2020,20, 398 3 of 31
3. Experimental verification of the method with ANN SCG that was devised for CO2concentration prediction (more one-day measurements in the period from 25 June 2018, to 28 June 2018) to locate an occupant (in rooms R104, R203, and R204) in an SH with the highest possible accuracy. 4. Experimental verification of the possibility of ANN learning for one room only (R203) in order to
predict CO2concentrations in other rooms (R104, R204).
The experimental measurements of objective parameters of the internal environment and thermal comfort evaluation were conducted in selected SH rooms R204, R203, and R104 in a wooden building of the passive standard located in the Faculty of Civil Engineering, VSB—TU Ostrava. (Figure1) [14].
Sensors 2020, 20, x FOR PEER REVIEW 3 of 29
3. Experimental verification of the method with ANN SCG that was devised for CO2 concentration prediction (more one-day measurements in the period from 25 June 2018, to 28 June 2018) to locate an occupant (in rooms R104, R203, and R204) in an SH with the highest possible accuracy. 4. Experimental verification of the possibility of ANN learning for one room only (R203) in order
to predict CO2 concentrations in other rooms (R104, R204).
The experimental measurements of objective parameters of the internal environment and thermal comfort evaluation were conducted in selected SH rooms R204, R203, and R104 in a wooden building of the passive standard located in the Faculty of Civil Engineering, VSB—TU Ostrava. (Figure 1) [14].
Figure 1. The wooden building of the passive standard located in the Faculty of Civil Engineering, VSB—TU Ostrava with selected smart home (SH) rooms R204, R203, and R104 [15].
2. Materials and Methods
2.1. Fiber Bragg Grating (FBG) Sensor Using for Recognition of Number Occupants in Smart Home (SH) Room R104
Bragg gratings (FBG) are special structures created by an ultraviolet (UV) laser inside the core of a photosensitive optical fibre. This structure consists of a periodic structure of changes in the refractive index, where the layers of the refractive index of the core 𝑛 alternate with the layers of the increased refractive index 𝑛 (1):
𝑛 = 𝑛 + 𝛿𝑛 (1)
where 𝛿𝑛 is the refractive index induced by UV radiation [16].
When a broad-spectrum light is introduced into the optical fibre, the Bragg grating reflects a narrow spectral portion and all the other wavelengths pass through the structure without damping (Figure 2).
Figure 2. The Bragg grating principle.
Figure 1. The wooden building of the passive standard located in the Faculty of Civil Engineering, VSB—TU Ostrava with selected smart home (SH) rooms R204, R203, and R104 [15].
2. Materials and Methods
2.1. Fiber Bragg Grating (FBG) Sensor Using for Recognition of Number Occupants in Smart Home (SH) Room R104
Bragg gratings (FBG) are special structures created by an ultraviolet (UV) laser inside the core of a photosensitive optical fibre. This structure consists of a periodic structure of changes in the refractive index, where the layers of the refractive index of the coren1alternate with the layers of the increased refractive indexn3(1):
n3=n1+δn (1)
whereδnis the refractive index induced by UV radiation [16].
When a broad-spectrum light is introduced into the optical fibre, the Bragg grating reflects a narrow spectral portion and all the other wavelengths pass through the structure without damping (Figure2).
Sensors 2020, 20, x FOR PEER REVIEW 3 of 29
3. Experimental verification of the method with ANN SCG that was devised for CO2 concentration
prediction (more one-day measurements in the period from 25 June 2018, to 28 June 2018) to locate an occupant (in rooms R104, R203, and R204) in an SH with the highest possible accuracy. 4. Experimental verification of the possibility of ANN learning for one room only (R203) in order
to predict CO2 concentrations in other rooms (R104, R204).
The experimental measurements of objective parameters of the internal environment and thermal comfort evaluation were conducted in selected SH rooms R204, R203, and R104 in a wooden building of the passive standard located in the Faculty of Civil Engineering, VSB—TU Ostrava. (Figure 1) [14].
Figure 1. The wooden building of the passive standard located in the Faculty of Civil Engineering, VSB—TU Ostrava with selected smart home (SH) rooms R204, R203, and R104 [15].
2. Materials and Methods
2.1. Fiber Bragg Grating (FBG) Sensor Using for Recognition of Number Occupants in Smart Home (SH) Room R104
Bragg gratings (FBG) are special structures created by an ultraviolet (UV) laser inside the core of a photosensitive optical fibre. This structure consists of a periodic structure of changes in the refractive index, where the layers of the refractive index of the core 𝑛 alternate with the layers of the increased refractive index 𝑛 (1):
𝑛 = 𝑛 + 𝛿𝑛 (1)
where 𝛿𝑛 is the refractive index induced by UV radiation [16].
When a broad-spectrum light is introduced into the optical fibre, the Bragg grating reflects a narrow spectral portion and all the other wavelengths pass through the structure without damping (Figure 2).
Sensors2020,20, 398 4 of 31
The central wavelength of the reflected spectral portion is called the Bragg wavelengthλBand is defined by the optical and geometric properties of the structure according to (2):
λB=2ne f fΛ (2)
wherene f f is the effective refractive index of the periodic structure andΛis the distance between the periodic changes in the refractive index. The external effects of the temperature and the deformation influence the optical and geometric properties and thus, the spectral position of the Bragg wavelength. Thanks to this feature, Bragg gratings are used in sensory applications. The dependence of the Bragg wavelength on the deformation and the temperature is expressed by (3):
∆λB
λB
=kε+ (αΛ+αn)∆T (3)
wherekis the deformation coefficient,εis the optical fibre deformation caused by measurement,αΛ is the coefficient of thermal expansion,αnis the thermo-optic coefficient and∆Tis the change in the operating temperature [17].
Bragg gratings in a standard optical fibre with a central wavelength of 1550 nm show a deformation sensitivity of 1.1 pm/µstrain and a temperature sensitivity of 10.3 pm/◦C. By using a suitable encapsulation, it is possible to implement a sensor of almost any physical quantity. FBG sensors are used in automobile [18] and railway transport [19], the construction industry [20], power engineering, biomedical [21] or perimetric applications [22], etc.
Bragg gratings are single-point sensors. By using a wavelength or time multiplex, it is possible to connect tens or hundreds of these sensors in a single optical fibre in order to achieve a quasi-distributed sensory system [23].
2.1.1. Fiberglass Bragg Sensors
One of the most widespread applications of Bragg gratings includes deformation and compression measurements. Depending on the type of application, Bragg gratings can be encapsulated in many ways. The principle of the encapsulation is to protect the fragile glass fibre, to enhance the sensitivity to the desired quantity and to suppress the surrounding interference. Bragg gratings can be encapsulated in polymers [24] of fibreglass or composite materials [25,26], and special steel jigs [27], which are mechanically attached to the structure that is to be measured, etc. Based on the advantages of using Bragg gratings—such as their reliable and very accurate measurement—these types of sensors were used for the reference measurement of the occupancy recognition of room R104 in the SH.
Because the grating sensors were installed on a wooden staircase, the encapsulation of Bragg gratings in fibreglass strips was used. This method enables the implementation of a very thin sensor that transmits deformations from the step (passage of persons) to the optical fibre itself.
Two Bragg gratings in a single-mode optical fibre with primary acrylate protection were used for implementing the sensors. Bragg gratings A and B had the following parameters: The Bragg wavelengths were 1547.510 nm and 1552.369 nm, respectively; the reflection spectrum width was 256 pm and 227 pm, respectively; the reflectivity was 91.2% and 91.3%, respectively. Each Bragg grating was placed between the glass fabrics (2 layers below and 2 layers above the optical fibre). The glass fabric was then coated with a polymer resin. The actual curing caused a Bragg wavelength shift of 23µm for Sensor A and of 19µm for Sensor B to lower wavelengths (Figure3). The Bragg grating is located in the middle of the fibreglass strip, marked in red.
Sensors2020,20, 398 5 of 31
Sensors 2020, 20, x FOR PEER REVIEW 4 of 29
The central wavelength of the reflected spectral portion is called the Bragg wavelength 𝜆 and is defined by the optical and geometric properties of the structure according to (2):
𝜆 = 2𝑛 Λ (2)
where 𝑛 is the effective refractive index of the periodic structure and Λ is the distance between the periodic changes in the refractive index. The external effects of the temperature and the deformation influence the optical and geometric properties and thus, the spectral position of the Bragg wavelength. Thanks to this feature, Bragg gratings are used in sensory applications. The dependence of the Bragg wavelength on the deformation and the temperature is expressed by (3):
Δ𝜆
𝜆 = 𝑘𝜀 + (𝛼 + 𝛼 )Δ𝑇 (3)
where 𝑘 is the deformation coefficient, 𝜀 is the optical fibre deformation caused by measurement, 𝛼 is the coefficient of thermal expansion, 𝛼 is the thermo-optic coefficient and Δ𝑇 is the change in the operating temperature [17].
Bragg gratings in a standard optical fibre with a central wavelength of 1550 nm show a deformation sensitivity of 1.1 pm/µstrain and a temperature sensitivity of 10.3 pm/°C. By using a suitable encapsulation, it is possible to implement a sensor of almost any physical quantity. FBG sensors are used in automobile [18] and railway transport [19], the construction industry [20], power engineering, biomedical [21] or perimetric applications [22], etc.
Bragg gratings are single-point sensors. By using a wavelength or time multiplex, it is possible to connect tens or hundreds of these sensors in a single optical fibre in order to achieve a quasi-distributed sensory system [23].
2.1.1. Fiberglass Bragg Sensors
One of the most widespread applications of Bragg gratings includes deformation and compression measurements. Depending on the type of application, Bragg gratings can be encapsulated in many ways. The principle of the encapsulation is to protect the fragile glass fibre, to enhance the sensitivity to the desired quantity and to suppress the surrounding interference. Bragg gratings can be encapsulated in polymers [24] of fibreglass or composite materials [25,26], and special steel jigs [27], which are mechanically attached to the structure that is to be measured, etc. Based on the advantages of using Bragg gratings—such as their reliable and very accurate measurement— these types of sensors were used for the reference measurement of the occupancy recognition of room R104 in the SH.
Because the grating sensors were installed on a wooden staircase, the encapsulation of Bragg gratings in fibreglass strips was used. This method enables the implementation of a very thin sensor that transmits deformations from the step (passage of persons) to the optical fibre itself.
Two Bragg gratings in a single-mode optical fibre with primary acrylate protection were used for implementing the sensors. Bragg gratings A and B had the following parameters: The Bragg wavelengths were 1547.510 nm and 1552.369 nm, respectively; the reflection spectrum width was 256 pm and 227 pm, respectively; the reflectivity was 91.2% and 91.3%, respectively. Each Bragg grating was placed between the glass fabrics (2 layers below and 2 layers above the optical fibre). The glass fabric was then coated with a polymer resin. The actual curing caused a Bragg wavelength shift of 23 µm for Sensor A and of 19 µm for Sensor B to lower wavelengths (Figure 3). The Bragg grating is located in the middle of the fibreglass strip, marked in red.
(a) (b)
Figure 3.Implementation of the sensor by encapsulating the Bragg grating in fibreglass (a); the resulting fibre Bragg grating (FBG) fibreglass sensor (b).
2.1.2. Implementation of FBG Sensors
FBG sensors were implemented on the staircase leading from the ground floor to the first floor (Figure4). The sensors were glued with cyanoacrylate adhesive to the bottom of the second step (FBG A) and the third step (FBG B).
Sensors 2020, 20, x FOR PEER REVIEW 5 of 29
Figure 3. Implementation of the sensor by encapsulating the Bragg grating in fibreglass (a); the resulting fibre Bragg grating (FBG) fibreglass sensor (b).
2.1.2. Implementation of FBG Sensors
FBG sensors were implemented on the staircase leading from the ground floor to the first floor (Figure 4). The sensors were glued with cyanoacrylate adhesive to the bottom of the second step (FBG A) and the third step (FBG B).
Figure 4. Placement of FBG sensors on the staircase in the smart home (SH), room R104.
2.2. Use of a CO2 Sensor Network for Monitoring SH Space Occupancy
Common CO2 sensors can be used to detect the occupancy of individual SH spaces. In room
R104, the BT 12.09 sensor (Figure 5), in room R203 the BT 12.10 sensor and in room R204 the BT 12.10 sensor (Figure 6) were used for measuring the CO2 concentration in the framework of forced Air
Condition (AC) control (Figure 7). The BACnet technology is used in the SH to control HVAC (Figure 8). The presence of occupants in the SH can be detected by measuring the CO2 concentration. Figure
5 shows the ground plan of the ground floor of the SH with the location of the individual sensors for CO2 measurement.
Figure 5. The ground plan of the ground floor of the SH with the location of the sensors for CO2
measurement.
The individual rooms on the ground floor of the SH are marked as follows (Figure 5):
• R101—door space, entrance hall,
• R102—toilet 1,
Figure 4.Placement of FBG sensors on the staircase in the smart home (SH), room R104. 2.2. Use of a CO2Sensor Network for Monitoring SH Space Occupancy
Common CO2sensors can be used to detect the occupancy of individual SH spaces. In room R104, the BT 12.09 sensor (Figure5), in room R203 the BT 12.10 sensor and in room R204 the BT 12.10 sensor (Figure6) were used for measuring the CO2concentration in the framework of forced Air Condition (AC) control (Figure7). The BACnet technology is used in the SH to control HVAC (Figure8). The presence of occupants in the SH can be detected by measuring the CO2concentration. Figure5 shows the ground plan of the ground floor of the SH with the location of the individual sensors for CO2measurement.
Sensors2020,20, 398 6 of 31
Sensors 2020, 20, x FOR PEER REVIEW 5 of 29
Figure 3. Implementation of the sensor by encapsulating the Bragg grating in fibreglass (a); the resulting fibre Bragg grating (FBG) fibreglass sensor (b).
2.1.2. Implementation of FBG Sensors
FBG sensors were implemented on the staircase leading from the ground floor to the first floor (Figure 4). The sensors were glued with cyanoacrylate adhesive to the bottom of the second step (FBG A) and the third step (FBG B).
Figure 4. Placement of FBG sensors on the staircase in the smart home (SH), room R104.
2.2. Use of a CO2 Sensor Network for Monitoring SH Space Occupancy
Common CO2 sensors can be used to detect the occupancy of individual SH spaces. In room
R104, the BT 12.09 sensor (Figure 5), in room R203 the BT 12.10 sensor and in room R204 the BT 12.10 sensor (Figure 6) were used for measuring the CO2 concentration in the framework of forced Air
Condition (AC) control (Figure 7). The BACnet technology is used in the SH to control HVAC (Figure 8). The presence of occupants in the SH can be detected by measuring the CO2 concentration. Figure
5 shows the ground plan of the ground floor of the SH with the location of the individual sensors for CO2 measurement.
Figure 5. The ground plan of the ground floor of the SH with the location of the sensors for CO2
measurement.
The individual rooms on the ground floor of the SH are marked as follows (Figure 5):
• R101—door space, entrance hall,
• R102—toilet 1,
Figure 5. The ground plan of the ground floor of the SH with the location of the sensors for CO2measurement.
Sensors 2020, 20, x FOR PEER REVIEW 6 of 29
• R103—toilet 2,
• R104—entrance room; FBG sensor is placed on the staircase,
• R105—utility room, there are heating sources,
• R106—classroom.
Figure 6 shows the ground plan of the first floor of the SH with the location of the individual sensors for CO2 measurement.
Figure 6. The ground plan of the first floor of the SH with the location of the sensors for CO2
measurement.
The individual rooms on the SH first floor are marked as follows (Figure 6):
• R201—staircase,
• R202—control room,
• R203—classroom (office),
• R204—classroom (office),
• R205—toilet and bathroom.
The list (legend) of the individual sensors used (Figures 5–7):
• BT 12.01—Measurement at the fresh outdoor air inlet into QPA 2062 SH.
• BT 12.02—Measurement at the recirculation air inlet from SH spaces into QPM 2162 heat recovery unit.
• BT 12.03—Measurement at the recirculation air inlet from SH spaces into QPA 2062 heat recovery unit.
• BT 12.04—Measurement in QFA 2060 heat recovery unit.
• BT 12.05—Measurement at the recirculation and fresh air outlet from the heat recovery unit into QFM 2160 SH.
• BT 12.06—Measurement at the exhaust air inlet into QFM 2160 recuperation unit.
• BT 12.07—Measurement at the exhaust air outlet from QPA 2062 recuperation unit.
• BT 12.08—Measurement at the recirculation air inlet from SH spaces into QPM 2162 heat recovery unit.
• BT 12.09—sensor located in room R104, QPA 2062.
• BT 12.10—sensor located in room R203, QPA 2062.
• BT 12.11—sensor located in room R204, QPA 2062. The technical specification of the individual sensors used:
• QPA 20.62 room sensor for measuring the air quality—CO2, relative humidity and
temperature—with a measurement accuracy: (50 ppm + 2% of the value measured, long-term Figure 6. The ground plan of the first floor of the SH with the location of the sensors for CO2measurement.
Sensors 2020, 20, x FOR PEER REVIEW 7 of 29
drift: 5% of the measuring range/5 years (typically). The CO2 sensor principle is based on non-dispersive infrared absorption (NDIR) measurement.
• QPM 21.62 channel sensors for air quality—CO2, relative humidity, temperature. Measurement accuracy: (50 ppm + 2% of the value measured), long-term drift: 5% of the measuring range/5 years (typically). The CO2 sensor is based on non-dispersive infrared absorption (NDIR) measurement.
• QFA 20.60 room sensor for temperature and relative humidity. Measurement accuracy ± 3% rHin within the comfort range. Application range −15 … +50 °C/0 … 95% rHin (no condensation). • QFM 21.60 channel sensor for relative humidity and temperature. Measurement accuracy ± 3%
rHin within the comfortable range. Application range −15 … +60 °C/0 … 95% rHin (no condensation).
Figure 7 shows the ventilation distribution technology with the location of the individual CO2 sensors.
Figure 7. The ventilation distribution technology with the location of the individual sensors for CO2
measurement in an SH.
A block diagram containing a description of the individual components and function blocks within the BACnet technology in the SH for HVAC control is shown in Figure 8.
Figure 8. Block diagram of the BACnet technology used in an SH for HVAC control.
2.3. The Design of the New Method for CO2Prediction
The newly devised method for CO2 prediction from the temperature indoor and relative humidity indoor values measured by means of ANN SCG (multiple one-day measurements) was used for the location of an occupant (in rooms R104, R203 a R204) in SH with the highest possible accuracy. Block diagram of processing the quantities measured in SH for multiple one-day
Figure 7.The ventilation distribution technology with the location of the individual sensors for CO2 measurement in an SH.
Sensors2020,20, 398 7 of 31
Sensors 2020, 20, x FOR PEER REVIEW 7 of 29
drift: 5% of the measuring range/5 years (typically). The CO2 sensor principle is based on
non-dispersive infrared absorption (NDIR) measurement.
• QPM 21.62 channel sensors for air quality—CO2, relative humidity, temperature. Measurement
accuracy: (50 ppm + 2% of the value measured), long-term drift: 5% of the measuring range/5 years (typically). The CO2 sensor is based on non-dispersive infrared absorption (NDIR)
measurement.
• QFA 20.60 room sensor for temperature and relative humidity. Measurement accuracy ± 3% rHin
within the comfort range. Application range −15 … +50 °C/0 … 95% rHin (no condensation).
• QFM 21.60 channel sensor for relative humidity and temperature. Measurement accuracy ± 3% rHin within the comfortable range. Application range −15 … +60 °C/0 … 95% rHin (no
condensation).
Figure 7 shows the ventilation distribution technology with the location of the individual CO2
sensors.
Figure 7. The ventilation distribution technology with the location of the individual sensors for CO2
measurement in an SH.
A block diagram containing a description of the individual components and function blocks within the BACnet technology in the SH for HVAC control is shown in Figure 8.
Figure 8. Block diagram of the BACnet technology used in an SH for HVAC control.
2.3. The Design of the New Method for CO2Prediction
The newly devised method for CO2 prediction from the temperature indoor and relative
humidity indoor values measured by means of ANN SCG (multiple one-day measurements) was used for the location of an occupant (in rooms R104, R203 a R204) in SH with the highest possible accuracy. Block diagram of processing the quantities measured in SH for multiple one-day
Figure 8.Block diagram of the BACnet technology used in an SH for HVAC control. The individual rooms on the ground floor of the SH are marked as follows (Figure5): • R101—door space, entrance hall,
• R102—toilet 1, • R103—toilet 2,
• R104—entrance room; FBG sensor is placed on the staircase, • R105—utility room, there are heating sources,
• R106—classroom.
Figure6shows the ground plan of the first floor of the SH with the location of the individual sensors for CO2measurement.
The individual rooms on the SH first floor are marked as follows (Figure6): • R201—staircase,
• R202—control room, • R203—classroom (office), • R204—classroom (office), • R205—toilet and bathroom.
The list (legend) of the individual sensors used (Figures5–7):
• BT 12.01—Measurement at the fresh outdoor air inlet into QPA 2062 SH.
• BT 12.02—Measurement at the recirculation air inlet from SH spaces into QPM 2162 heat recovery unit.
• BT 12.03—Measurement at the recirculation air inlet from SH spaces into QPA 2062 heat recovery unit.
• BT 12.04—Measurement in QFA 2060 heat recovery unit.
• BT 12.05—Measurement at the recirculation and fresh air outlet from the heat recovery unit into QFM 2160 SH.
• BT 12.06—Measurement at the exhaust air inlet into QFM 2160 recuperation unit. • BT 12.07—Measurement at the exhaust air outlet from QPA 2062 recuperation unit.
• BT 12.08—Measurement at the recirculation air inlet from SH spaces into QPM 2162 heat recovery unit.
• BT 12.09—sensor located in room R104, QPA 2062. • BT 12.10—sensor located in room R203, QPA 2062. • BT 12.11—sensor located in room R204, QPA 2062.
Sensors2020,20, 398 8 of 31
• QPA 20.62 room sensor for measuring the air quality—CO2, relative humidity and temperature—with a measurement accuracy: (50 ppm+2% of the value measured, long-term drift: 5% of the measuring range/5 years (typically). The CO2sensor principle is based on non-dispersive infrared absorption (NDIR) measurement.
• QPM 21.62 channel sensors for air quality—CO2, relative humidity, temperature. Measurement accuracy: (50 ppm+2% of the value measured), long-term drift: 5% of the measuring range/5 years (typically). The CO2sensor is based on non-dispersive infrared absorption (NDIR) measurement. • QFA 20.60 room sensor for temperature and relative humidity. Measurement accuracy±3% rHin
within the comfort range. Application range−15. . . +50◦C/0. . . 95% rHin(no condensation). • QFM 21.60 channel sensor for relative humidity and temperature. Measurement accuracy±
3% rHin within the comfortable range. Application range−15. . . +60 ◦
C/0. . . 95% rHin (no condensation).
Figure 7 shows the ventilation distribution technology with the location of the individual CO2sensors.
A block diagram containing a description of the individual components and function blocks within the BACnet technology in the SH for HVAC control is shown in Figure8.
2.3. The Design of the New Method for CO2Prediction
The newly devised method for CO2prediction from the temperature indoor and relative humidity indoor values measured by means of ANN SCG (multiple one-day measurements) was used for the location of an occupant (in rooms R104, R203 a R204) in SH with the highest possible accuracy. Block diagram of processing the quantities measured in SH for multiple one-day measurements in the period from 25 June 2018, to 28 June 2018, using the method devised for CO2prediction by means of ANN SCG is shown in Figure9.
Sensors 2020, 20, x FOR PEER REVIEW 8 of 29
measurements in the period from 25 June 2018, to 28 June 2018, using the method devised for CO2
prediction by means of ANN SCG is shown in Figure 9.
Figure 9. Block diagram describing processing of the data measured by means of a scaled conjugate gradient artificial neural network (ANN SCG) within the method devised for CO2 prediction.
The measured values that were used in these experiments are the indoor CO2 concentration,
indoor relative humidity and indoor temperature. The data were pre-processed to improve the efficiency of neural network training. That means that data were normalized so that all the values are between 0 and 1 (Figure 10, Step 1).
Figure 10. Block scheme summarizing the experiment steps.
In Matlab, the function nftool (neural fitting) was used with neurons varying from 10 to 100 and the three methods previously mentioned. The data samples were divided into 3 sets: training (used to teach the network), validation and testing (provides an independent measure of the network training) (Figure 10, Step 2). After training the networks with data measured on 25 July for room 203, the 90 networks were used to predict data for the rest of the dates from the same room, as well as the two others. Since the learning date was different from the prediction dates, this was called “cross-validation”. In this step, the function used in Matlab was ‘nntool’ (Figure 10, Step 3). Once the results were ready, the next step was to calculate some parameters that would allow us to quantify the precision of the results, and, therefore, compare the prediction quality between the different ANN SCG (Figure 10, Step 4).
The three parameters we relied on for our experiments are as follows.
R (correlation coefficient) is a statistical measure that calculates the strength of the relationship between the relative movements of two variables and is calculated with the formula (4). The values range between −1 and 1. A value of exactly 1.0 means there is a perfect positive relationship between the two variables. For a positive increase in one variable, there is also a positive increase in the second variable. A value of −1.0 means there is a perfect negative relationship between the two variables. This shows that the variables move in opposite directions—for a positive increase in one variable, there is a decrease in the second variable. If the correlation is 0, there is no relationship between the two variables [28].
𝑅 = ∑(𝑥 − 𝑥̅)(𝑦 − 𝑦)
∑(𝑥 − 𝑥̅) ∑(𝑦 − 𝑦) (4)
Figure 9.Block diagram describing processing of the data measured by means of a scaled conjugate gradient artificial neural network (ANN SCG) within the method devised for CO2prediction.
The measured values that were used in these experiments are the indoor CO2concentration, indoor relative humidity and indoor temperature. The data were pre-processed to improve the efficiency of neural network training. That means that data were normalized so that all the values are between 0 and 1 (Figure10, Step 1).
Sensors2020,20, 398 9 of 31
Sensors 2020, 20, x FOR PEER REVIEW 8 of 29
measurements in the period from 25 June 2018, to 28 June 2018, using the method devised for CO2
prediction by means of ANN SCG is shown in Figure 9.
Figure 9. Block diagram describing processing of the data measured by means of a scaled conjugate gradient artificial neural network (ANN SCG) within the method devised for CO2 prediction.
The measured values that were used in these experiments are the indoor CO2 concentration,
indoor relative humidity and indoor temperature. The data were pre-processed to improve the efficiency of neural network training. That means that data were normalized so that all the values are between 0 and 1 (Figure 10, Step 1).
Figure 10. Block scheme summarizing the experiment steps.
In Matlab, the function nftool (neural fitting) was used with neurons varying from 10 to 100 and the three methods previously mentioned. The data samples were divided into 3 sets: training (used to teach the network), validation and testing (provides an independent measure of the network training) (Figure 10, Step 2). After training the networks with data measured on 25 July for room 203, the 90 networks were used to predict data for the rest of the dates from the same room, as well as the two others. Since the learning date was different from the prediction dates, this was called “cross-validation”. In this step, the function used in Matlab was ‘nntool’ (Figure 10, Step 3). Once the results were ready, the next step was to calculate some parameters that would allow us to quantify the precision of the results, and, therefore, compare the prediction quality between the different ANN SCG (Figure 10, Step 4).
The three parameters we relied on for our experiments are as follows.
R (correlation coefficient) is a statistical measure that calculates the strength of the relationship between the relative movements of two variables and is calculated with the formula (4). The values range between −1 and 1. A value of exactly 1.0 means there is a perfect positive relationship between the two variables. For a positive increase in one variable, there is also a positive increase in the second variable. A value of −1.0 means there is a perfect negative relationship between the two variables. This shows that the variables move in opposite directions—for a positive increase in one variable, there is a decrease in the second variable. If the correlation is 0, there is no relationship between the two variables [28].
𝑅 = ∑(𝑥 − 𝑥̅)(𝑦 − 𝑦)
∑(𝑥 − 𝑥̅) ∑(𝑦 − 𝑦) (4)
Figure 10.Block scheme summarizing the experiment steps.
In Matlab, the function nftool (neural fitting) was used with neurons varying from 10 to 100 and the three methods previously mentioned. The data samples were divided into 3 sets: training (used to teach the network), validation and testing (provides an independent measure of the network training) (Figure10, Step 2). After training the networks with data measured on 25 July for room 203, the 90 networks were used to predict data for the rest of the dates from the same room, as well as the two others. Since the learning date was different from the prediction dates, this was called “cross-validation”. In this step, the function used in Matlab was ‘nntool’ (Figure10, Step 3). Once the results were ready, the next step was to calculate some parameters that would allow us to quantify the precision of the results, and, therefore, compare the prediction quality between the different ANN SCG (Figure10, Step 4).
The three parameters we relied on for our experiments are as follows.
R (correlation coefficient) is a statistical measure that calculates the strength of the relationship between the relative movements of two variables and is calculated with the formula (4). The values range between−1 and 1. A value of exactly 1.0 means there is a perfect positive relationship between the two variables. For a positive increase in one variable, there is also a positive increase in the second variable. A value of−1.0 means there is a perfect negative relationship between the two variables. This shows that the variables move in opposite directions—for a positive increase in one variable, there is a decrease in the second variable. If the correlation is 0, there is no relationship between the two variables [28]. R= P (x−x)(y−y) q P (x−x)2P (y−y)2 (4)
The MSE (mean squared error) parameter describes how close a regression line is to a set of points and is calculated with formula (5). It does this by taking the distances from the points to the regression line (these distances are the “errors”) and squaring them. The squaring is necessary to remove any negative signs. It also gives more weight to larger differences. It is called the mean squared error as you are finding the average of a set of errors [29]:
MSE= 1 n n X i=1 yi−y ∗ i (5)
MAPE (average absolute percentage error) is a statistical measurement parameter of how accurate a forecast system is. It measures this accuracy as a percentage, and it can be calculated as the average absolute percent error for each time period minus actual values divided by actual values which are given by (6) [30]: MAPE= 1 n n X i=1 yi−y ∗ i y∗i (6) yi: reference value, y∗i: predicted value, n: total number of values, x,y: mean of x, y.
After calculating the MAPE, MSE, and R correlation parameters, we plot two figures. The first one has a reference and predicted CO2over time (Figures 18, 20 and 22) and the second one is a
Sensors2020,20, 398 10 of 31
Bland–Altmann plot (Figures 19, 21 and 23). The Bland–Altman technique allows us to make a comparison between two measurement methods of the same sample. It was established by J. Martin Bland and Douglas G. Altman. Essentially, it quantifies the difference between measurements using a graphical method. It consists of a scatterplot with the average and the difference represented on the X-axis and theY-axis, respectively. The plot also has horizontal lines drawn at the mean difference and at the limits of agreement, which are defined as the mean difference plus and minus 1.96 times the standard deviation of the differences (Figure10, Step 5). The final step is to compare the results and the plots, so as to decide which conditions and which methods are optimal for future predictions.
The procedure used to carry out the learning process in the neural networks is called optimization algorithms. In the following experiments, a ANN SCG type of mathematical algorithm was used to train the ANNs.
ScaledConjugateGradientAlgorithm:
SCG is a supervised learning algorithm for feedforward neural networks and is a member of the class of conjugate gradient methods (CGMs). Letp=exp−∆TEbe a vector, N the sum of the number of weights and of the number of biases of the network, andEthe error function we want to minimize. SCG differs from other conjugate gradient methods in two ways [31]:
Each iteration k of a CGM computesωi, whereRN is a new conjugate direction, andωk+1 =
ωk+αk.pkis the size of the step in this direction. In fact,pkis a function ofαk, the Hessian matrix of the error function, namely the matrix of the second derivatives. In contrast to other CGMs that avoid the complex computation of the Hessian and approximateαkwith a time-consuming line search procedure, SCG makes the following simple approximation of the termE00
(ωk), a key component of the computation ofαk:sk[32] as the Hessian is not always positive, which prevents the algorithm from achieving good performance; SCG uses a scalarαkwhich is supposed to regulate the indefiniteness of the Hessian. This resembles the Levenberg–Marquardt method, and is performed by using the following equation (7) [33]: sk=E 00 (ωk).pk≈ E0(ωk+αk.pk)−E0(ωk) αk , 0< αk1 (7)
and adjustingλkat each iteration.
The final step is to compare the results and the plots, so as to decide which conditions and which methods are optimal for future predictions [34].
2.4. The Signed–Regressor LMS Adaptive Filter
The signed–regressor LMS adaptive filter was used to filter the predicted course in order to determine the occupancy of the monitored areas more precisely (Figures 19, 21, 23, 26, 28 and 30). 2.4.1. The Conventional LMS Algorithm
The LMS algorithm is a linear adaptive filtering algorithm, which consists of two basic processes: (a) a filtering process, which involves computing the outputy(n) of the linear filter in response to an input signalx(n) (8), generating an estimation errore(n) by comparing this outputy(n) with the desired responsed(n) (9),
(b) an adaptive process (10), which involves the automatic adjustment of the parametersw(n+1) of the filter in accordance with the estimation errore(n).
y(n) = M−1 X i=0 wi(n)x(n−i) (8) e(n) =d(n)−y(n) (9)
Sensors2020,20, 398 11 of 31
w(n+1) =w(n) +2µe(n)x(n) (10) wherew(n) isMtap—weight vector,w(n+1) isMtap—weight vector update [35,36].
2.4.2. The Signed–Regressor LMS Algorithm
The signed–regressor algorithm is obtained from the conventional recursion (10) by replacing the tap-input vectorx(n) with the vector sign(x(n)), where the sign function is applied to the vectorx(n) on an element-by-element basis. The signed–regressor recursion is then [35]:
w(n+1)=w(n)+2µe(n)sign(x(n)) (11) 3. Experiments and Results
3.1. Using Fiber Bragg Grating Sensor for Recognition of Number of Occupants in SH Room R104
The results of the experiments to detect the number of occupants in the monitored space of room R104 are described below. On 25 June 2018, we installed the individual sensors (FBG A and FBG B) on the staircase in room R104 (Figure4). The actual measurement to unambiguously detect the number of occupants in the monitored space took place from 25 to 28 June 2018. The record of the continuous measurement conducted in the period from 25 to 28 June 2018, is shown in Figure11. These are signals from the Bragg sensors where the individual peaks represent persons treading on a particular step. Blue shows the waveform of the FBG A sensor on the second step and red shows the signal from FBG B sensor on the third step.Sensors 2020, 20, x FOR PEER REVIEW 11 of 29
Figure 11. The waveform of signals from FBG A and FBG B sensors during the 24-h measurement of recognition of the number occupants in room R104 in the period from 25 June 2018 (7:48:00), to 28 June 2018 (23:59:00).
To detect the number of occupants on the first floor, an algorithm was implemented in the MATLAB (Matrix Laboratory) computational software environment. The algorithm is based on the detection of peaks (treading on the step) from both FBG sensors. The time-corresponding peaks were compared over time, while the direction of the passage (up or down) was detected based on earlier treading on the first or second step. The number of occupants on the first floor was detected using a counter. The occupancy waveform of the first floor is shown in Figure 12.
Figure 12. First floor of the recognition of the number occupants obtained from the measurement conducted in the period from 25 June 2018 (7:48:00), to 28 June 2018 (23:59:00).
The number of occupants can be detected from the following Table 1:
Figure 11.The waveform of signals from FBG A and FBG B sensors during the 24-h measurement of recognition of the number occupants in room R104 in the period from 25 June 2018 (7:48:00), to 28 June 2018 (23:59:00).
To detect the number of occupants on the first floor, an algorithm was implemented in the MATLAB (Matrix Laboratory) computational software environment. The algorithm is based on the detection of peaks (treading on the step) from both FBG sensors. The time-corresponding peaks were compared over time, while the direction of the passage (up or down) was detected based on earlier treading on the first or second step. The number of occupants on the first floor was detected using a counter. The occupancy waveform of the first floor is shown in Figure12.
Sensors2020,20, 398 12 of 31
Sensors 2020, 20, x FOR PEER REVIEW 11 of 29
Figure 11. The waveform of signals from FBG A and FBG B sensors during the 24-h measurement of recognition of the number occupants in room R104 in the period from 25 June 2018 (7:48:00), to 28 June 2018 (23:59:00).
To detect the number of occupants on the first floor, an algorithm was implemented in the MATLAB (Matrix Laboratory) computational software environment. The algorithm is based on the detection of peaks (treading on the step) from both FBG sensors. The time-corresponding peaks were compared over time, while the direction of the passage (up or down) was detected based on earlier treading on the first or second step. The number of occupants on the first floor was detected using a counter. The occupancy waveform of the first floor is shown in Figure 12.
Figure 12. First floor of the recognition of the number occupants obtained from the measurement conducted in the period from 25 June 2018 (7:48:00), to 28 June 2018 (23:59:00).
The number of occupants can be detected from the following Table 1:
Figure 12. First floor of the recognition of the number occupants obtained from the measurement conducted in the period from 25 June 2018 (7:48:00), to 28 June 2018 (23:59:00).
The number of occupants can be detected from the following Table1:
Table 1.Unambiguous determination of the number of occupants on the staircase in room R104 in the SH. Date Time Number of
Occupants Date Time
Number of
Occupants Date Time
Number of Occupants (dd.mm.yyyy) (hh:mm:ss) (dd.mm.yyyy) (hh:mm:ss) (dd.mm.yyyy) (hh:mm:ss)
25 June 2018 7:48:07 1 27 June 2018 9:40:24 2 27 June 2018 14:52:53 2 25 June 2018 7:53:11 1 27 June 2018 9:44:09 3 27 June 2018 14:53:13 3 25 June 2018 7:53:13 2 27 June 2018 9:47:55 2 27 June 2018 14:56:13 2 25 June 2018 7:53:23 1 27 June 2018 9:51:23 1 27 June 2018 14:56:49 3 26 June 2018 8:49:04 1 27 June 2018 9:52:31 2 27 June 2018 15:01:32 2 26 June 2018 8:59:39 1 27 June 2018 10:04:16 3 27 June 2018 15:02:11 3 26 June 2018 9:21:15 1 27 June 2018 10:06:44 2 27 June 2018 15:12:12 2 26 June 2018 9:55:43 2 27 June 2018 10:08:47 1 27 June 2018 15:13:37 2 26 June 2018 10:29:44 1 27 June 2018 10:09:10 2 27 June 2018 15:13:41 3 26 June 2018 10:54:16 1 27 June 2018 10:21:31 1 27 June 2018 15:14:28 2 26 June 2018 11:49:18 1 27 June 2018 11:25:30 2 27 June 2018 15:14:50 3 26 June 2018 12:34:02 2 27 June 2018 11:29:22 3 27 June 2018 15:15:49 2 26 June 2018 12:35:40 1 27 June 2018 11:33:34 2 27 June 2018 15:22:19 3 26 June 2018 14:38:27 2 27 June 2018 11:36:08 1 27 June 2018 15:23:10 2 26 June 2018 15:24:31 1 27 June 2018 11:36:48 0 27 June 2018 16:18:22 1 26 June 2018 15:24:52 2 27 June 2018 12:28:48 1 27 June 2018 16:18:46 0 26 June 2018 16:07:57 1 27 June 2018 12:28:57 2 28 June 2018 8:54:33 1 26 June 2018 16:08:25 2 27 June 2018 12:53:14 1 28 June 2018 8:54:35 2 26 June 2018 16:31:34 1 27 June 2018 13:03:53 2 28 June 2018 9:22:11 1 27 June 2018 8:33:55 1 27 June 2018 14:25:57 1 28 June 2018 10:19:19 1 27 June 2018 8:35:22 2 27 June 2018 14:26:27 2 28 June 2018 10:20:05 2 27 June 2018 9:07:51 1 27 June 2018 14:29:00 3 28 June 2018 10:59:54 1 27 June 2018 9:09:36 2 27 June 2018 14:30:04 2 28 June 2018 11:00:07 2
Sensors2020,20, 398 13 of 31
Table 1.Cont.
Date Time Number of
Occupants Date Time
Number of
Occupants Date Time
Number of Occupants (dd.mm.yyyy) (hh:mm:ss) (dd.mm.yyyy) (hh:mm:ss) (dd.mm.yyyy) (hh:mm:ss)
27 June 2018 9:26:26 1 27 June 2018 14:33:03 1 28 June 2018 12:23:23 1 27 June 2018 9:30:32 2 27 June 2018 14:44:50 2 28 June 2018 12:45:23 2 27 June 2018 9:34:57 1 27 June 2018 14:45:09 1 28 June 2018 15:01:41 1 27 June 2018 9:35:50 2 27 June 2018 14:46:08 2 28 June 2018 15:01:57 2 27 June 2018 9:39:48 1 27 June 2018 14:51:29 3 28 June 2018 16:22:41 1
Discussion—Experiment 3.1:
On the basis of measuring the movement of occupants on the staircase in room R104 using FBG sensors in the period from 26 to 29 June 2019, it is possible to clearly identify the number of occupants (Figure12) in the monitored SH space (Figure4)—specifically in room R104 (Figure5)—with an accuracy of 1 s. Within the initial testing of the experiment conducted, two persons walking up the stairs to the first floor of the SH were detected on 25 June 2018, when installing the FBG sensors in the SH (room R104) (Figure12), (Table1). On 26 June 2018, movement of one and two persons on the staircase from the ground floor to the first floor was detected during the day (Figure12), (Table1). On 27 June 2018, and 29 June 2018, movement of one, two and three persons was detected during the day. On 28 June the movement of one and two persons was detected during the day (Figure12), (Table1). The drawback of this method of using the FBG sensor to detect the number of occupants in the monitored space is the lack of information on the occupancy of the monitored space of R104 in the SH. This drawback has been eliminated by adding CO2sensors to rooms R104, R203 and R204 in experiment 2, which is described below.
3.2. Use of CO2Sensors for Monitoring SH Space Occupancy
CO2sensors (R104 (BT12.09), R203 (BT12.10), R204 (BT12.11)) can be used to detect occupancy of the monitored spaces (rooms R104, R203, R204) in the SH (Figures5and6); these sensors are used to control the quality of the indoor environment in these rooms using BACnet technology in the SH (Figure7). To control HVAC in SH (Figure7), other CO2sensors which provide “measurement at the fresh outdoor air inlet into QPA 2062 SH (BT 12.01) were used; measurement at the recirculation air inlet from SH spaces into the QPM 2162 heat recovery unit (BT 12.02); measurement at the recirculation air inlet from SH spaces into the QPA 2062 heat recovery unit (BT 12.03); measurement in the QFA 2060 heat recovery unit (BT 12.04); measurement at the recirculation and fresh air outlet from the heat recovery unit into the QFM 2160 SH (BT 12.05); measurement at the exhaust air inlet into the QFM 2160 recuperation unit (BT 12.06); measurement at the exhaust air outlet from the QPA 2062 recuperation unit (BT 12.07); measurement at the recirculation air inlet from SH spaces into the QPM 2162 heat recovery unit (BT 12.08)”.
Discussion—Experiment 3.2:
Using the information from the FBG sensor (Figure13), it is possible to unambiguously detect the number of occupants present in the monitored space. Based on the measured values (CO2 concentration), it is possible to detect the occupancy of the monitored SH spaces, the arrival of a person into the monitored room or the exit from the monitored space, or the length of stay in the monitored space (Figures14–16). The aforementioned procedure enables the unambiguous determination of the occupancy rate of the monitored SH spaces, indirectly by measuring common non-electrical quantities (CO2) within the operational–technical function control in the SH.
Sensors2020,20, 398 14 of 31
Sensors 2020, 20, x FOR PEER REVIEW 13 of 29
2062 recuperation unit (BT 12.07); measurement at the recirculation air inlet from SH spaces into the QPM 2162 heat recovery unit (BT 12.08)”.
Discussion—Experiment 3.2:
Using the information from the FBG sensor (Figure 13), it is possible to unambiguously detect the number of occupants present in the monitored space. Based on the measured values (CO2
concentration), it is possible to detect the occupancy of the monitored SH spaces, the arrival of a person into the monitored room or the exit from the monitored space, or the length of stay in the monitored space (Figures 14–16). The aforementioned procedure enables the unambiguous determination of the occupancy rate of the monitored SH spaces, indirectly by measuring common non-electrical quantities (CO2) within the operational–technical function control in the SH.
However, if the building is of an administrative type, the acquisition of CO2 sensors for dozens
of rooms is a major investment. In market research, we ascertained that CO2 sensors are two to three
times (in some cases, greater) more expensive than temperature and humidity sensors, which are, moreover, a common part of individual rooms in administrative buildings in the Czech Republic.
Due to the higher costs of acquiring CO2 sensors, we proposed the possibility of lowering the
initial investment costs for larger administrative buildings by providing information about the occupancy of the individual rooms within the newly devised method of CO2 prediction. The
mathematical method of ANN SCG was used to predict the waveform of CO2 concentration using
the values measured from indoor temperature (Tin) and indoor relative humidity (rHin) sensors. The
experiments performed within the newly devised method are presented in the following text.
Figure 13. Waveforms of the CO2 concentration values measured in SH rooms R104 (BT 12.09), R203
(BT 12.10), R204 (BT 12.11) in order to detect the occupancy of the monitored spaces with the representation of the recognition of the number of occupants in room R104 using the FBG sensor. Figure 13.Waveforms of the CO2concentration values measured in SH rooms R104 (BT 12.09), R203 (BT 12.10), R204 (BT 12.11) in order to detect the occupancy of the monitored spaces with the representation of the recognition of the number of occupants in room R104 using the FBG sensor.
Sensors 2020, 20, x FOR PEER REVIEW 14 of 29
Figure 14. Waveforms of the CO2 concentration values measured in SH room R104 (BT 12.09).
Figure 15. Waveforms of the CO2 concentration values measured in SH room R203 (BT 12.10). Figure 14.Waveforms of the CO2concentration values measured in SH room R104 (BT 12.09).
Sensors2020,20, 398 15 of 31
Sensors 2020, 20, x FOR PEER REVIEW 14 of 29
Figure 14. Waveforms of the CO2 concentration values measured in SH room R104 (BT 12.09).
Figure 15. Figure 15.Waveforms of the COWaveforms of the CO22 concentration values measured in SH room R203 (BT 12.10). concentration values measured in SH room R203 (BT 12.10).
Sensors 2020, 20, x FOR PEER REVIEW 15 of 29
Figure 16. Waveforms of the CO2 concentration values measured in SH room R204 (BT 12.11).
3.3. Experimental Verification of the Method with the Devised Artificial Neural Network (ANN) Scaled Conjugate Gradient (SCG)
The conditions of experiments 3.3a and 3.3b were as follows. The experiments were performed for the waveforms of temperature (Tin), relative humidity (rHin) and CO2 concentration measured on
26 June 2018, 27 June 2018, and 28 June 2018, (step 1) for rooms R104, R203 and R204 (Figure 17).
Figure 17. The waveform of the experiments performed on 26 June 2018, 27 June 2018, and 28 June 2018 for rooms R104, R203 and R204.
Furthermore, the measured data were pre-processed (step 2) (Figure 17). The design of the prediction system structure (step 3), the implementation (step 4) and ANN SCG training (step 5) for CO2 prediction using two input values of temperature (Tin) and relative humidity (rHin) were carried
Figure 16.Waveforms of the CO2concentration values measured in SH room R204 (BT 12.11).
However, if the building is of an administrative type, the acquisition of CO2sensors for dozens of rooms is a major investment. In market research, we ascertained that CO2sensors are two to three times (in some cases, greater) more expensive than temperature and humidity sensors, which are, moreover, a common part of individual rooms in administrative buildings in the Czech Republic.
Due to the higher costs of acquiring CO2sensors, we proposed the possibility of lowering the initial investment costs for larger administrative buildings by providing information about the occupancy of the individual rooms within the newly devised method of CO2prediction. The mathematical method of ANN SCG was used to predict the waveform of CO2concentration using the values measured from
Sensors2020,20, 398 16 of 31
indoor temperature (Tin) and indoor relative humidity (rHin) sensors. The experiments performed within the newly devised method are presented in the following text.
3.3. Experimental Verification of the Method with the Devised Artificial Neural Network (ANN) Scaled Conjugate Gradient (SCG)
The conditions of experiments 3.3a and 3.3b were as follows. The experiments were performed for the waveforms of temperature (Tin), relative humidity (rHin) and CO2concentration measured on 26 June 2018, 27 June 2018, and 28 June 2018, (step 1) for rooms R104, R203 and R204 (Figure17).
Sensors 2020, 20, x FOR PEER REVIEW 15 of 29
Figure 16. Waveforms of the CO2 concentration values measured in SH room R204 (BT 12.11).
3.3. Experimental Verification of the Method with the Devised Artificial Neural Network (ANN) Scaled Conjugate Gradient (SCG)
The conditions of experiments 3.3a and 3.3b were as follows. The experiments were performed for the waveforms of temperature (Tin), relative humidity (rHin) and CO2 concentration measured on
26 June 2018, 27 June 2018, and 28 June 2018, (step 1) for rooms R104, R203 and R204 (Figure 17).
Figure 17. The waveform of the experiments performed on 26 June 2018, 27 June 2018, and 28 June 2018 for rooms R104, R203 and R204.
Furthermore, the measured data were pre-processed (step 2) (Figure 17). The design of the prediction system structure (step 3), the implementation (step 4) and ANN SCG training (step 5) for CO2 prediction using two input values of temperature (Tin) and relative humidity (rHin) were carried
Figure 17.The waveform of the experiments performed on 26 June 2018, 27 June 2018, and 28 June 2018 for rooms R104, R203 and R204.
Furthermore, the measured data were pre-processed (step 2) (Figure17). The design of the prediction system structure (step 3), the implementation (step 4) and ANN SCG training (step 5) for CO2prediction using two input values of temperature (Tin) and relative humidity (rHin) were carried out. The ANN SCG structure designed (Figure18) for experiment 3.3a was trained (step 5) for the temperature (Tin), relative humidity (rHin) and CO2concentration values measured in room R203. The actual CO2prediction (step 6) was implemented for the data measured in rooms R104, R203 and R204. To increase the accuracy of the newly devised method, an additional quantity from the FBG sensor containing the number of occupants in the monitored space of R104 was added to the original two input quantities. The ANN SCG structure designed for experiment 3.3b for CO2prediction using three input quantities—temperature (Tin), relative humidity (rHin) and the number of occupants (FBG sensor). The procedure for performing the experiments was the same as that described in Figure17.
Sensors2020,20, 398 17 of 31
Sensors 2020, 20, x FOR PEER REVIEW 16 of 29
out. The ANN SCG structure designed (Figure 18) for experiment 3.3a was trained (step 5) for the temperature (Tin), relative humidity (rHin) and CO2 concentration values measured in room R203. The
actual CO2 prediction (step 6) was implemented for the data measured in rooms R104, R203 and R204.
To increase the accuracy of the newly devised method, an additional quantity from the FBG sensor containing the number of occupants in the monitored space of R104 was added to the original two input quantities. The ANN SCG structure designed for experiment 3.3b for CO2 prediction using
three input quantities—temperature (Tin), relative humidity (rHin) and the number of occupants (FBG
sensor). The procedure for performing the experiments was the same as that described in Figure 17. Experiment 3.3a:
Input values, Tin and rHin, to ANN SCG for prediction of CO2 in rooms R203, R204, and R104
(Figure 18). Prediction of CO2 in rooms R203, R204, R104 for the dates 26, 27 and 28 June 2018 with
inputs Tin and rHin, using learned ANN SCG (Figure 18) from 25 June 2018. Tables 2–4 show R, MSE
and MAPE parameter values, followed by plots of reference and predicted CO2, as well as Bland–
Altmann plots in rooms 203 (Figures 19 and 20), 204 (Figures 21 and 22) and 104 (Figures 23 and 24).
Figure 18. The architecture of the designed ANN SCG on test data measured in R203 from 25 June 2018 for two inputs Tin and rHin without and FBG sensor for person presence measuring (PPM). Table 2. Learned ANN SCG from 25 June 2018 in R203 (with Tin and rHin) and prediction with
cross-validation for 26 June 2018 in R203 (with TinandrHin), 27 June 2018 in R203 (with Tin and rHin), 28 June
2018 in R203 (with TinandrHin).
26 June 2018 in R203 27 June 2018 in R203 28 June 2018 in R203 Number of Neurons
ANN SCG
MSE R MAPE MSE R MAPE MSE R MAPE
(-) (-) (-) (-) (-) (-) (-) (-) (-) 10 0.0062 0.8867 0.2858 0.006 0.5094 0.198 0.0206 0.6398 0.3275 20 0.0063 0.8846 0.289 0.006 0.5098 0.1992 0.0204 0.6449 0.3238 30 0.0058 0.8943 0.2872 0.0058 0.5355 0.1794 0.0198 0.6586 0.3265 40 0.0071 0.8728 0.3237 0.0056 0.5555 0.2036 0.0193 0.6687 0.3186 50 0.0047 0.9151 0.2171 0.0056 0.5591 0.1633 0.0138 0.7784 0.212 60 0.006 0.8918 0.3298 0.0061 0.5084 0.1906 0.0103 0.8401 0.1818 70 0.0059 0.8957 0.3025 0.0054 0.5824 0.1861 0.0127 0.7983 0.2091 80 0.0048 0.9145 0.2475 0.0059 0.5261 0.1845 0.0127 0.7988 0.2558 90 0.0069 0.877 0.1623 0.0065 0.4645 0.2097 0.0106 0.8346 0.2221 100 0.0047 0.916 0.2559 0.0047 0.6489 0.1614 0.0111 0.8266 0.1884 Figure 18.The architecture of the designed ANN SCG on test data measured in R203 from 25 June 2018 for two inputsTinand rHinwithout and FBG sensor for person presence measuring (PPM).
Experiment 3.3a:
Input values,Tinand rHin, to ANN SCG for prediction of CO2in rooms R203, R204, and R104 (Figure18). Prediction of CO2in rooms R203, R204, R104 for the dates 26, 27 and 28 June 2018 with inputsTinand rHin, using learned ANN SCG (Figure18) from 25 June 2018. Tables2–4show R, MSE and MAPE parameter values, followed by plots of reference and predicted CO2, as well as Bland–Altmann plots in rooms 203 (Figures19and20), 204 (Figures21and22) and 104 (Figures23and24).
Table 2. Learned ANN SCG from 25 June 2018 in R203 (withTin and rHin) and prediction with cross-validation for 26 June 2018 in R203 (withTinand rHin), 27 June 2018 in R203 (withTinand rHin), 28 June 2018 in R203 (withTinand rHin).
26 June 2018 in R203 27 June 2018 in R203 28 June 2018 in R203 Number of Neurons
ANN SCG
MSE R MAPE MSE R MAPE MSE R MAPE
(-) (-) (-) (-) (-) (-) (-) (-) (-) 10 0.0062 0.8867 0.2858 0.006 0.5094 0.198 0.0206 0.6398 0.3275 20 0.0063 0.8846 0.289 0.006 0.5098 0.1992 0.0204 0.6449 0.3238 30 0.0058 0.8943 0.2872 0.0058 0.5355 0.1794 0.0198 0.6586 0.3265 40 0.0071 0.8728 0.3237 0.0056 0.5555 0.2036 0.0193 0.6687 0.3186 50 0.0047 0.9151 0.2171 0.0056 0.5591 0.1633 0.0138 0.7784 0.212 60 0.006 0.8918 0.3298 0.0061 0.5084 0.1906 0.0103 0.8401 0.1818 70 0.0059 0.8957 0.3025 0.0054 0.5824 0.1861 0.0127 0.7983 0.2091 80 0.0048 0.9145 0.2475 0.0059 0.5261 0.1845 0.0127 0.7988 0.2558 90 0.0069 0.877 0.1623 0.0065 0.4645 0.2097 0.0106 0.8346 0.2221 100 0.0047 0.916 0.2559 0.0047 0.6489 0.1614 0.0111 0.8266 0.1884
Sensors2020,20, 398 18 of 31
Table 3. Learned ANN SCG from 25 June 2018 in R203 (withTin and rHin) and prediction with cross-validation for 26 June 2018 in R204 (withTinand rHin), 27 June 2018 in R204 (withTinand rHin), and 28 June 2018 in R204 (withTinand rHin).
26 June 2018 in R204 27 June 2018 in R204 28 June 2018 in R204 Number of Neurons
ANN SCG
MSE R MAPE MSE R MAPE MSE R MAPE
(-) (-) (-) (-) (-) (-) (-) (-) (-) 10 0.0107 0.6276 0.2117 0.0112 0.2603 0.209 0.0187 0.4399 0.1699 20 0.0117 0.5816 0.2634 0.0057 0.7272 0.156 0.0087 0.8007 0.1154 30 0.0116 0.5914 0.2917 0.0049 0.7726 0.1232 0.0186 0.4429 0.1678 40 0.0104 0.6402 0.2231 0.0058 0.7213 0.1535 0.0074 0.825 0.1015 50 0.0103 0.6482 0.2425 0.0061 0.7017 0.1387 0.0186 0.4407 0.1692 60 0.0122 0.5606 0.2589 0.0054 0.7425 0.1463 0.0077 0.817 0.11 70 0.0111 0.6125 0.2503 0.0073 0.6261 0.1668 0.0077 0.8159 0.1065 80 0.0106 0.6354 0.2188 0.0052 0.7551 0.1133 0.0085 0.7971 0.1174 90 0.0111 0.6228 0.1671 0.0052 0.7555 0.1458 0.0077 0.8178 0.1078 100 0.0109 0.6232 0.2742 0.0048 0.7755 0.1404 0.0104 0.7416 0.1202
Table 4. Learned ANN SCG from 25 June 2018 in R203 (withTin and rHin) and prediction with cross-validation for 26 June 2018 in R104 (withTinand rHin), 27 June 2018 in R104 (withTinand rHin), and 28 June 2018 in R104 (withTinand rHin).
26 June 2018 in R104 27 June 2018 in R104 28 June 2018 in R104 Number of Neurons
ANN SCG
MSE R MAPE MSE R MAPE MSE R MAPE
(-) (-) (-) (-) (-) (-) (-) (-) (-) 10 0.0097 0.6714 0.3365 0.0121 0.2188 0.2147 0.0187 0.4399 0.1694 20 0.0102 0.6516 0.2259 0.0052 0.7541 0.1466 0.0186 0.4418 0.1713 30 0.0105 0.6398 0.2233 0.0061 0.7052 0.1395 0.0187 0.4396 0.1699 40 0.0099 0.6643 0.2074 0.0055 0.7389 0.144 0.0128 0.6684 0.1197 50 0.0098 0.6685 0.2099 0.0059 0.7136 0.1319 0.0186 0.4411 0.1692 60 0.0098 0.6697 0.2044 0.0055 0.7387 0.1544 0.0025 0.9135 0.0905 70 0.0099 0.6626 0.1937 0.0056 0.7345 0.1464 0.0082 0.8031 0.1089 80 0.0101 0.6542 0.2063 0.0051 0.7567 0.1134 0.0096 0.7676 0.1121 90 0.0095 0.6822 0.1859 0.0051 0.7613 0.1429 0.0085 0.7959 0.1216 100 0.01 0.6587 0.2005 0.0043 0.8027 0.1202 0.0077 0.8175 0.1041
Sensors 2020, 20, x FOR PEER REVIEW 17 of 29
Figure 19. Comparison of the reference CO2 concentration waveform and predicted CO2 waveforms
(SRLMS AF) from 26 June 2018 in R203 with an ANN with 100 neurons and SCG method trained with data from 25 June 2018 in R203.
Figure 20. Bland–Altman plot for the reference and predicted CO2 waveforms (SRLMS AF) from 26
June 2018 in R203 with an ANN with 100 neurons and SCG method trained with data from 25 June 2018 in R203.
Table 3. Learned ANN SCG from 25 June 2018 in R203 (with Tin and rHin) and prediction with
cross-validation for 26 June 2018 in R204 (with Tin and rHin), 27 June 2018 in R204 (with Tin and rHin), and 28
June 2018 in R204 (with Tin and rHin).
26 June 2018 in R204 27 June 2018 in R204 28 June 2018 in R204
Number of Neurons ANN SCG
MSE R MAPE MSE R MAPE MSE R MAPE
(-) (-) (-) (-) (-) (-) (-) (-) (-)
10 0.0107 0.6276 0.2117 0.0112 0.2603 0.209 0.0187 0.4399 0.1699
20 0.0117 0.5816 0.2634 0.0057 0.7272 0.156 0.0087 0.8007 0.1154
Figure 19.Comparison of the reference CO2concentration waveform and predicted CO2waveforms (SRLMS AF) from 26 June 2018 in R203 with an ANN with 100 neurons and SCG method trained with data from 25 June 2018 in R203.
